Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    리에
    -0.07
    させる
    -0.07
     кип
    -0.07
    eksiyon
    -0.06
     форма
    -0.06
    aş
    -0.06
     tallest
    -0.06
    へと
    -0.06
    ��
    -0.06
     فایل
    -0.06
    POSITIVE LOGITS
    Complete
    0.08
    .city
    0.07
     jouer
    0.06
     dest
    0.06
    .jdbc
    0.06
     Settings
    0.06
     bargaining
    0.06
    .over
    0.06
     Boy
    0.06
     cram
    0.06
    Act Density 0.033%

    No Known Activations